GPT 4o Transcribe Diarize

OpenAI

openai/gpt-4o-transcribe-diarize

Transcription with speaker diarization

Context Window

—

Max Output

—

About this model

GPT-4o Transcribe Diarize adds speaker diarization on top of GPT-4o Transcribe's capabilities. It automatically identifies different speakers and labels each segment with the corresponding speaker.

Perfect for meeting minutes, interview transcripts, podcast transcription, and any scenario where "who said what" matters.

Highlights

Speaker identification

Outperforms Whisper

Structured output

Multi-speaker support

Best For

Meeting minutesInterview transcriptsPodcast transcriptionCourt recordings

2025-10-15

Capabilities

STT

Aliases

gpt-4o-transcribe-diarize

Pricing (per 1M tokens)

Pricing (per 1M tokens)	/ 1M tokens
Input / 1M	$6.30
Output / 1M	$10.50

Final prices shown

Quick Start

main.py

from openai import OpenAI

client = OpenAI(
    base_url="https://api.chuizi.ai/v1",
    api_key="ck-your-key-here",
)

with open("audio.mp3", "rb") as f:
    transcript = client.audio.transcriptions.create(
        model="openai/gpt-4o-transcribe-diarize",
        file=f,
    )
print(transcript.text)